Zarif
AI Automation Builder & Educator
Zarif builds AI agents and automation workflows and writes about what holds up in production: the sources worth following, the roles the AI era is creating, and agent workflows you can inspect end to end.
What you can inspect
The site backs its guidance with maintained sources, runnable examples, and work you can review directly.
What I Do
I build AI agents and automation workflows, and I work at n8n. This site is where I write down what holds up: which sources are worth following, what forward-deployed and AI-engineering roles actually involve, and how real agent workflows are put together. The writing comes from building and shipping these systems, and the directories include source links, selection notes, and verification dates.
Demonstrated Work
Below is one of the three n8n workflows I publish in the open, run against its sample lead so you can see the scoring rules, the response, and the setup it needs. It shows the workflow's behavior with test data, rather than measured client results.
INSPECTABLE EXAMPLE · LEAD INTAKE, ENRICHMENT, AND ROUTING · FREE PACK v1.0.1
What one free workflow actually does with a lead
This demonstration runs the published workflow against its included test fixture. The rules are the scoring expressions inside the export, and the output is the response the webhook returns. It shows the workflow's behavior, not measured customer results.
Input · fixtures.json → success
{
"leadId": "lead_demo_1001",
"name": "Jordan Lee",
"email": "jordan@example.com",
"company": "Example Co",
"companySize": 12,
"budget": 2500,
"source": "website",
"notes": "We need help automating lead response and qualification."
}Visible rules · score and route
- Budget 2,500 (1,000 or more)+25
- Company size 12 (5 or more)+20
- Notes 56 characters (40 or more)+20
- Score (capped at 100)65
- Route is priority only when budget is 5,000 or more or company size is 20 or more. This lead meets neither, so it routes as standard.
Output · HTTP 202
{
"accepted": true,
"leadId": "lead_demo_1001",
"route": "standard",
"acknowledgementQueued": true
}Invalid input "invalid" · HTTP 400
{
"accepted": false,
"error": "A valid name and email are required."
}What it does not do
- The export ships inactive and credential-free. You add the header-auth and SMTP credentials before it can run.
- Nothing is persisted. The caller is responsible for storing the accepted lead and its route.
- It replies 202 before sending mail, so a lead can be acknowledged even if the acknowledgement email later fails.
- There is no duplicate detection, delivery log, or error-trigger workflow. Those are production concerns the starter leaves to you.
- Open-source GTM skills — evidence-first agent skills you can read before you install them.
- Start here — reading paths through sources, roles, and agent workflows.
Where to Find Me
- YouTube — Builds recorded end to end
- Twitter / X — Daily notes on agents, automation, and who is worth reading
Why This Site Exists
AI tooling changes weekly, and the hard part is knowing which sources, roles, and patterns deserve attention. This site keeps maintained lists of who to follow, a clear path into AI-engineering roles, and agent workflows you can inspect end to end, so you spend your time choosing useful tools and building with them.